使用方法
- 复制安装命令，在自己的智能体环境安装前先检查源码包。
- 从原始文档核对所需工具、凭据和支持的宿主。
- 说明输入材料与期望交付物，并对照来源检查输出。
npx skills add https://github.com/aaron-he-zhu/aaron-marketing-skills --skill narrative-quality-auditor开始前需了解
- 安装不包含模型订阅、API 额度或访问文件的权限。
- 仓库星数和安装量反映活跃情况，不等于独立质量或安全测试。
按源仓库内容呈现，保留标题、案例、代码、表格、链接以及原文引用的演示图片。
Narrative Quality Auditor
Audit narrative truth, message-system coherence, or measured effectiveness as separate TALE profiles. There is no v18 overall composite: truth cannot be averaged away by coherence, and coherence cannot stand in for effectiveness evidence.
When This Must Trigger
- The user asks whether positioning/differentiation is defensible.
- A flagship surface needs a pre-publish canon/message-match gate.
- A message experiment or resonance claim needs evidence-integrity review.
- A full narrative review is requested; run linked profiles rather than one blended score.
Quick Start
Run TALE truth on canon v7 against named alternatives and approved claims.
Run TALE system on homepage/pricing/deck against canon v7 before release.
Run a full review as three linked profile results; do not compute an overall score.Skill Contract
Reads: one canon/surface set or message experiment plus current narrative/claims truth. Writes: only permissioned v3 artifacts. Done when: each requested profile is independently complete or its Unknowns are explicit, with no canon, claims, or surface mutation.
narrative-registry owns canon/version state and offer-claims-registry owns claims. This skill judges; authoring/fixing belongs to Trace/Architect/Land skills.
Data Sources
| Need | Preferred evidence |
|---|---|
| Truth | Named alternatives, interviews/win-loss, product reality, claims projection |
| Architecture | Exact canon/version, message hierarchy, voice/naming/version history |
| Landing | Declared rendered flagship surfaces linked to canon version |
| Effectiveness | Preregistered comprehension/recall/behavior evidence and locked panels |
| Public resonance | Dated own/public signals with explicit measured/proxy provenance |
Instructions
Runtime Reads
../../../references/auditor-runbook.md../../../references/scoring-semantics.md../../../references/tale-benchmark.md../../../references/runtime-invocation.mdreferences/auditor-runtime.md
Runtime and Setup
Read ../../../references/auditor-runbook.md, scoring-semantics.md, tale-benchmark.md, and the TALE catalog entry. Standalone installs use bundled immutable references/auditor-runtime.md; never fetch mutable main. Before deterministic calls, follow `runtime-invocation.md`, resolve AARON_SKILLS_ROOT="${CLAUDE_PLUGIN_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || true)}", and require the scorer, validator, and typed catalogs. If unavailable, still collect the selected profile's typed observations and Unknowns, but return score_state: NOT_SCORED / score_confidence: not_scored with no gate verdict or persistent artifact; runtime absence blocks deterministic scoring, not the observation pass.
Declare target, profile/mode, brand scope, market, audience, canon version, observation date, and evidence window.
Profile Procedure
- `truth`: score T1–T10 for material differentiation and factual grounding.
- `system`: score A1–A10 and L1–L10 for canon coherence and landing consistency.
- `effectiveness`: score E1–E10 for one experiment/locked panel/date.
- `full`: run the three profiles independently and keep three artifacts/results. Aggregate release language conservatively: any BLOCK → block; otherwise any UNDECIDED → undecided; otherwise any FIX → fix; all SHIP → ship. Never average scores.
For a flagship pre-publish gate, always execute the system profile procedure and require a compatible current truth result. If no compatible truth result exists, run truth separately when its evidence is available; otherwise record the truth prerequisite as Unknown while still rendering the requested system-profile result. A missing scorer/runtime changes that result to NOT_SCORED/UNDECIDED; it does not justify skipping the profile. Run effectiveness separately only when the user requests it or the surface makes an effectiveness claim.
Every observed state needs source/date/type/confidence. A missing canon is Unknown, not N/A. A2/A4/A8 are conditional: three pillars, a change arc, and fixed boilerplate lengths are patterns only when deliberately chosen. Run the typed scorer per profile.
Verify profile-relevant vetoes: TALE-T1 false/contradictory/unsubstantiated material differentiation, TALE-A1 demonstrated canon contradiction, TALE-L1 material flagship/canon contradiction, and TALE-E1 unsupported effectiveness claim or proxy-as-measured.
§2 TALE Worked Examples
- Complete truth profile, raw 86, no veto/fail:
DONE/SHIP, final 86. - Complete system profile, raw 80, one verified L1 failure:
DONE_WITH_CONCERNS/FIX, final 59. - Complete system profile with A1 and L1 failures:
DONE/BLOCK, no final score. - Effectiveness profile before test results exist:
NEEDS_INPUT/UNDECIDED, no score.
§3 TALE Guardrails
- A literal “onlyness” sentence is not required; judge the material differentiation actually asserted.
- Three pillars, a Raskin/change arc, and 25/50/100-word boilerplates are conditional patterns.
- A governed draft can be audited as a draft; missing access is Unknown, not an A1 failure.
- Share of voice, sentiment, answer-engine descriptions, comprehension, and behavior are distinct constructs.
- Narrative change frequency is a drift signal, not an automatic veto.
§5 TALE Translation
Always name truth/system/effectiveness. On trace request, qualify TALE-T1/A1/L1/E1, especially TALE-E1 versus ECHO-E1 and TALE-A1 versus ROAS/RAMP.
Report and Verdict
Begin with the auditor-runbook's exact typed conversation header. Never replace status, verdict, or score_state with prose; list each explicitly missing qualified item as `ID: unknown``` before findings.
For each profile show verdict, target/canon/context/date, score or coverage/interval, confidence, evidence, Unknowns, and fixes. A full report shows three side-by-side results and no overall number. Do not claim market effectiveness from system coherence.
Validation Checkpoints
- One profile/unit per score; full mode preserves three results.
- Canon/surface/experiment versions and audience/market are explicit.
- Conditional templates use N/A only with reason; missing evidence stays Unknown.
- Current truth/claims projections are read, not candidate files.
- No canon/claim/surface write or publish action occurred.
Persistence
Persist only after explicit authorization to memory/audits/narrative/YYYY-MM-DD-<topic>-<profile>.md. Preserve the scorer's orthogonal status and verdict; validate the complete v3 draft with validate-audit-artifact.py against the intended relative path, persist only through one full-content Write, and revalidate the target per the auditor runbook. Edit/shell/MCP mutations of the reserved sink are unsupported. Never overwrite another profile or update canon/claims/hot cache autonomously.
Reference Materials
Next Best Skill
- Truth repair: positioning-truth-tracer
- Architecture repair: message-system-architect
- Landing repair: narrative-cascade-planner
- Effectiveness evidence: message-test-designer
